Performance test of Naive Bayes and SVM methods on classification of malnutrition status in children

Devie Rosa Anamisa, Achmad Jauhari, Fifin Ayu Mufarroha

Abstract


Paying attention to children's nutrition is very important because children's daily activity is relatively high. Therefore, one of the efforts that the Indonesian Government must make is to reduce the incidence of malnutrition because high malnutrition can increase the death rate. In recent years, Madura Island has experienced an increase in the number of children suffering from stunting, especially in the Sumenep area. Therefore, it is necessary to collect data to handle it quickly and validly. However, to explore data, classification techniques are needed. Given these problems, this research has carried out a comparative analysis with two classifier methods, namely Naïve Bayes and Support Vector Machine (SVM) to categorize malnutrition in children. Both methods have advantages. The Naïve Bayes method can be used to make predictions based on the probability of members of a malnutrition category class. Meanwhile, SVM can classify based on the kernel to form the best hyperplane on the input data. Based on 694 data on malnutrition in children, the SVM method has produced the best level of accuracy with a value of 89.76% with a Kernel Polynomial at a Cost (C) of 5 compared to the Naïve Bayes method of 86.31%. Thus, it can be concluded that the SVM method can classify malnutrition very well.

Full Text: PDF

Published: 2024-03-04

How to Cite this Article:

Devie Rosa Anamisa, Achmad Jauhari, Fifin Ayu Mufarroha, Performance test of Naive Bayes and SVM methods on classification of malnutrition status in children, Commun. Math. Biol. Neurosci., 2024 (2024), Article ID 25

Copyright © 2024 Devie Rosa Anamisa, Achmad Jauhari, Fifin Ayu Mufarroha. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Commun. Math. Biol. Neurosci.

ISSN 2052-2541

Editorial Office: [email protected]

 

Copyright ©2024 CMBN